{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From:\n",
    "\n",
    "- [BERT Fine-Tuning Tutorial with PyTorch · Chris McCormick](http://mccormickml.com/2019/07/22/BERT-fine-tuning/)\n",
    "- [huggingface/pytorch-transformers: 👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)](https://github.com/huggingface/pytorch-transformers)\n",
    "\n",
    "\n",
    "Fine-Tuning:\n",
    "\n",
    "- Easy Training: recommend 2-4 epochs on a special NLP task\n",
    "- Less Data\n",
    "- Good Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler\n",
    "from keras.preprocessing.sequence import pad_sequences\n",
    "from sklearn.model_selection import train_test_split\n",
    "from pytorch_transformers import BertTokenizer, BertConfig\n",
    "from pytorch_transformers import BertForSequenceClassification, BertModel\n",
    "from pytorch_transformers.optimization import AdamW, WarmupLinearSchedule\n",
    "from tqdm import tqdm, trange\n",
    "import pandas as pd\n",
    "import io\n",
    "import os\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```bash\n",
    "# download glue data\n",
    "$ git clone https://gist.github.com/60c2bdb54d156a41194446737ce03e2e.git download_glue_repo\n",
    "$ python download_glue_repo/download_glue_data.py --data_dir='glue_data'\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# [The Corpus of Linguistic Acceptability (CoLA)](https://nyu-mll.github.io/CoLA/)\n",
    "data_path = \"cola_public/raw/\"\n",
    "train_path = os.path.join(data_path, \"in_domain_train.tsv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(train_path, delimiter='\\t', header=None, \n",
    "                 names=['sentence_source', 'label', 'label_notes', 'sentence'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sentence_source</th>\n",
       "      <th>label</th>\n",
       "      <th>label_notes</th>\n",
       "      <th>sentence</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>668</th>\n",
       "      <td>bc01</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>I expect John to win and Harry to lose.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7090</th>\n",
       "      <td>sgww85</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Some people go by car, but others by bike.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997</th>\n",
       "      <td>rhl07</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Martha gave Myrna an apple.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4314</th>\n",
       "      <td>ks08</td>\n",
       "      <td>0</td>\n",
       "      <td>*</td>\n",
       "      <td>It tried to rain.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6406</th>\n",
       "      <td>d_98</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>We didn't keep a list of the names, but the Pr...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     sentence_source  label label_notes  \\\n",
       "668             bc01      1         NaN   \n",
       "7090          sgww85      1         NaN   \n",
       "1997           rhl07      1         NaN   \n",
       "4314            ks08      0           *   \n",
       "6406            d_98      1         NaN   \n",
       "\n",
       "                                               sentence  \n",
       "668             I expect John to win and Harry to lose.  \n",
       "7090         Some people go by car, but others by bike.  \n",
       "1997                        Martha gave Myrna an apple.  \n",
       "4314                                  It tried to rain.  \n",
       "6406  We didn't keep a list of the names, but the Pr...  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "sentences = df.sentence.values\n",
    "sentences = [\"[CLS] \" + sentence + \" [SEP]\" for sentence in sentences]\n",
    "labels = df.label.values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Input"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The default download path is ~/.cache\n",
    "tokenizer = BertTokenizer.from_pretrained(\"bert-base-uncased\", do_lower_case=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tokenize the first sentence:\n",
      "['[CLS]', 'our', 'friends', 'won', \"'\", 't', 'buy', 'this', 'analysis', ',', 'let', 'alone', 'the', 'next', 'one', 'we', 'propose', '.', '[SEP]']\n"
     ]
    }
   ],
   "source": [
    "tokenized_texts = [tokenizer.tokenize(sent) for sent in sentences]\n",
    "print (\"Tokenize the first sentence:\")\n",
    "print (tokenized_texts[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['i', 'love', 'you']"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.tokenize(\"i love you\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "30522"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.vocab_size"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Format:\n",
    "\n",
    "- input ids: index in BERT tokenizer vocabulary\n",
    "- segment mask: a sequence of 1s and 0s used to identify whether the input is one sentence or two sentences.\n",
    "- attention mask: a sequence of 1s and 0s, with 1s for input tokens and 0s for padding ones.\n",
    "- labels: a single 0 or 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "MAX_LEN = 16"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_ids = pad_sequences([tokenizer.convert_tokens_to_ids(s) for s in tokenized_texts],\n",
    "                         maxlen=MAX_LEN, dtype=\"long\", truncating=\"post\", padding=\"post\")\n",
    "# \"post\" means padding or truncating at the end of the sequence."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "attn_masks = []\n",
    "for seq in input_ids:\n",
    "    seq_mask = [float(i>0) for i in seq]\n",
    "    attn_masks.append(seq_mask)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "8551"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(attn_masks)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "8551"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(input_ids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_inputs, validation_inputs, train_labels, validation_labels = train_test_split(\n",
    "    input_ids, labels, random_state=2018, test_size=0.1)\n",
    "train_masks, validation_masks, _, _ = train_test_split(\n",
    "    attn_masks, input_ids, random_state=2018, test_size=0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_inputs = torch.tensor(train_inputs)\n",
    "validation_inputs = torch.tensor(validation_inputs)\n",
    "train_labels = torch.tensor(train_labels)\n",
    "validation_labels = torch.tensor(validation_labels)\n",
    "train_masks = torch.tensor(train_masks)\n",
    "validation_masks = torch.tensor(validation_masks)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "batch_size = 32\n",
    "train_data = TensorDataset(train_inputs, train_masks, train_labels)\n",
    "train_sampler = RandomSampler(train_data)\n",
    "train_dataloader = DataLoader(train_data, sampler=train_sampler, batch_size=batch_size)\n",
    "\n",
    "validation_data = TensorDataset(validation_inputs, validation_masks, validation_labels)\n",
    "validation_sampler = SequentialSampler(validation_data)\n",
    "validation_dataloader = DataLoader(validation_data, sampler=validation_sampler, batch_size=batch_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([7695, 16])"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_inputs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([7695])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_labels.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "# need to download the base uncased model, 420M\n",
    "# The default download path is ~/.cache\n",
    "model1 = BertForSequenceClassification.from_pretrained(\"bert-base-uncased\", num_labels=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "model2 = BertModel.from_pretrained(\"bert-base-uncased\", num_labels=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_ids = torch.tensor(tokenizer.encode(\"Hello, my dog is cute\")).unsqueeze(0)  # Batch size 1\n",
    "outputs1 = model1(input_ids)\n",
    "outputs2 = model2(input_ids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(tensor([[0.0587, 0.2715]], grad_fn=<AddmmBackward>),)"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "outputs1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "encoder_out, text_cls = outputs2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[[[-0.0103, -0.1227,  0.3213,  ..., -0.1227,  0.1663,  0.8999],\n",
       "          [-0.1704,  0.1079,  0.1188,  ...,  0.1253,  0.2631,  0.7764],\n",
       "          [-0.1531,  0.1066,  0.0684,  ...,  0.2248,  0.2979,  0.8439],\n",
       "          [-0.2531,  0.1373, -0.2181,  ...,  0.0539,  0.2127,  0.7677],\n",
       "          [-0.5390, -0.1542,  0.0448,  ...,  0.0955,  0.1294,  0.7215],\n",
       "          [-0.5359, -0.1256,  0.1278,  ...,  0.1238,  0.3003,  0.3731]]]],\n",
       "       grad_fn=<UnsqueezeBackward0>)"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "encoder_out.unsqueeze(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{\n",
       "  \"attention_probs_dropout_prob\": 0.1,\n",
       "  \"finetuning_task\": null,\n",
       "  \"hidden_act\": \"gelu\",\n",
       "  \"hidden_dropout_prob\": 0.1,\n",
       "  \"hidden_size\": 768,\n",
       "  \"initializer_range\": 0.02,\n",
       "  \"intermediate_size\": 3072,\n",
       "  \"layer_norm_eps\": 1e-12,\n",
       "  \"max_position_embeddings\": 512,\n",
       "  \"num_attention_heads\": 12,\n",
       "  \"num_hidden_layers\": 12,\n",
       "  \"num_labels\": 2,\n",
       "  \"output_attentions\": false,\n",
       "  \"output_hidden_states\": false,\n",
       "  \"torchscript\": false,\n",
       "  \"type_vocab_size\": 2,\n",
       "  \"vocab_size\": 30522\n",
       "}"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model1.config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{\n",
       "  \"attention_probs_dropout_prob\": 0.1,\n",
       "  \"finetuning_task\": null,\n",
       "  \"hidden_act\": \"gelu\",\n",
       "  \"hidden_dropout_prob\": 0.1,\n",
       "  \"hidden_size\": 768,\n",
       "  \"initializer_range\": 0.02,\n",
       "  \"intermediate_size\": 3072,\n",
       "  \"layer_norm_eps\": 1e-12,\n",
       "  \"max_position_embeddings\": 512,\n",
       "  \"num_attention_heads\": 12,\n",
       "  \"num_hidden_layers\": 12,\n",
       "  \"num_labels\": 2,\n",
       "  \"output_attentions\": false,\n",
       "  \"output_hidden_states\": false,\n",
       "  \"torchscript\": false,\n",
       "  \"type_vocab_size\": 2,\n",
       "  \"vocab_size\": 30522\n",
       "}"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model2.config"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hyperparamters recommended:\n",
    "\n",
    "- Batch size: 16, 32\n",
    "- Learning rate (Adam): 5e-5, 3e-5, 2e-5\n",
    "- Number of epochs: 2, 3, 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "param_optimizer = list(model.named_parameters())\n",
    "no_decay = ['bias', 'gamma', 'beta']\n",
    "optimizer_grouped_parameters = [\n",
    "    {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)],\n",
    "     'weight_decay_rate': 0.01},\n",
    "    {'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)],\n",
    "     'weight_decay_rate': 0.0}\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer = AdamW(optimizer_grouped_parameters, lr=2e-5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_train_optimization_steps = int(len(train_data) / batch_size / 1) * 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "scheduler = WarmupLinearSchedule(optimizer, warmup_steps=100, t_total=num_train_optimization_steps)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "def flat_accuracy(preds, labels):\n",
    "    pred_flat = np.argmax(preds, axis=1).flatten()\n",
    "    labels_flat = labels.flatten()\n",
    "    return np.sum(pred_flat == labels_flat) / len(labels_flat)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_loss_set = []\n",
    "\n",
    "# Number of training epochs (authors recommend between 2 and 4)\n",
    "epochs = 4\n",
    "\n",
    "# trange is a tqdm wrapper around the normal python range\n",
    "for _ in trange(epochs, desc=\"Epoch\"):\n",
    "\n",
    "    # Training\n",
    "\n",
    "    # Set our model to training mode (as opposed to evaluation mode)\n",
    "    model.train()\n",
    "    # Tracking variables\n",
    "    tr_loss = 0\n",
    "    nb_tr_examples, nb_tr_steps = 0, 0\n",
    "\n",
    "    # Train the data for one epoch\n",
    "    for step, batch in enumerate(train_dataloader):\n",
    "        # Add batch to GPU\n",
    "#         batch = tuple(t.to(device) for t in batch)\n",
    "        # Unpack the inputs from our dataloader\n",
    "        b_input_ids, b_input_mask, b_labels = batch\n",
    "        # Clear out the gradients (by default they accumulate)\n",
    "        optimizer.zero_grad()\n",
    "        # Forward pass\n",
    "        outputs = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask, labels=b_labels)\n",
    "        loss = outputs[0]\n",
    "        train_loss_set.append(loss.item())    \n",
    "        # Backward pass\n",
    "        loss.backward()\n",
    "        # Update parameters and take a step using the computed gradient\n",
    "        optimizer.step()\n",
    "        scheduler.step()\n",
    "\n",
    "        # Update tracking variables\n",
    "        tr_loss += loss.item()\n",
    "        nb_tr_examples += b_input_ids.size(0)\n",
    "        nb_tr_steps += 1\n",
    "\n",
    "        print(\"Train loss: {}\".format(tr_loss/nb_tr_steps))\n",
    "\n",
    "\n",
    "    # Validation\n",
    "\n",
    "    # Put model in evaluation mode to evaluate loss on the validation set\n",
    "    model.eval()\n",
    "\n",
    "    # Tracking variables \n",
    "    eval_loss, eval_accuracy = 0, 0\n",
    "    nb_eval_steps, nb_eval_examples = 0, 0\n",
    "\n",
    "    # Evaluate data for one epoch\n",
    "    for batch in validation_dataloader:\n",
    "        # Add batch to GPU\n",
    "#         batch = tuple(t.to(device) for t in batch)\n",
    "        # Unpack the inputs from our dataloader\n",
    "        b_input_ids, b_input_mask, b_labels = batch\n",
    "        # Telling the model not to compute or store gradients, saving memory and speeding up validation\n",
    "        with torch.no_grad():\n",
    "          # Forward pass, calculate logit predictions\n",
    "          logits = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask)\n",
    "\n",
    "        # Move logits and labels to CPU\n",
    "        logits = logits.detach().cpu().numpy()\n",
    "        label_ids = b_labels.to('cpu').numpy()\n",
    "\n",
    "        tmp_eval_accuracy = flat_accuracy(logits, label_ids)\n",
    "\n",
    "        eval_accuracy += tmp_eval_accuracy\n",
    "        nb_eval_steps += 1\n",
    "\n",
    "        print(\"Validation Accuracy: {}\".format(eval_accuracy/nb_eval_steps))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15,8))\n",
    "plt.title(\"Training loss\")\n",
    "plt.xlabel(\"Batch\")\n",
    "plt.ylabel(\"Loss\")\n",
    "plt.plot(train_loss_set)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}